- Statistical Methods for Multivariate Missing Data in Health Survey Research.
-
Dong Kee Kim, Eun Cheol Park, Myong Sei Sohn, Han Joong Kim, Hyung Uk Park, Chae Hyung Ahn, Jong Gun Lim, Ki Jun Song
-
Korean J Prev Med. 1998;31(4):875-884.
-
-
-
 Abstract
 PDF
- Missing observations are common in medical research and health survey research. Several statistical methods to handle the missing data problem have been proposed. The EM algorithm (Expectation-Maximization algorithm) is one of the ways of efficiently handling the missing data problem based on sufficient statistics. In this paper, we developed statistical models and methods for survey data with multivariate missing observations. Especially, we adopted the Em algorithm to handle the multivariate missing observations. We assume that the multivariate observations follow a multivariate normal distribution, where the mean vector and the covariance matrix are primarily of interest. We applied the proposed statistical method to analyze data from a health survey. The data set we used came from a physician survey on Resource-Based Relative Value Scale(RBRVS). In addition to the EM algorithm, we applied the complete case analysis, which used only completely observed cases, and the available case analysis, which utilizes all available information. The residual and normal probability plots were evaluated to access the assumption of normality. We found that the residual sum of squares from the EM algorithm was smaller than those of the complete-case and the available-case analyses.
-
Summary
- Analysis of influencing factors on self-employed physician's income.
-
Woong Sub Park, Han Joong Kim, Myong Sei Sohn, Eun Cheol Park
-
Korean J Prev Med. 1998;31(4):770-785.
-
-
-
Abstract
PDF
- This study describes the relation of physician's income and price of medical service and social welfare through microeconomic view, reviews the literature of influencing factor on physician's income, and it describes general distribution of physician's income, and analyzes influencing factor of physician's income. A total of 844 persons responded to the mail survey, through stratified sampling by 23 branches of medical society in Korean RBRVS study. The design of the study is cross sectional study, and the unit of analysis is a physician. To examine the change of average income per month, multiple regression was used to test the change according to physician's characteristics, demographic characteristics, scale of clinic(or hospital), average intensity of ordinary work, and specialty. The major findings of this study are as follows; 1. As for self-employed physicians, the difference of average income per month among specialties was 4,850,000won, but the difference was 6,020,000won under the control of control variables, and average income per month was significantly higher for physicians who had sick-beds than physicians who had no sick-beds. 2. The number of average out-patients per month and number of nurses and nursing aides significantly positively associated, but the number of physician significantly negatively associated with average income per month. In conclusion, the number of out-patient and number of nurses and nursing aides is the major influencing factor, and the difference of average income per month among specialties existed in self-employed physicians. So this study suggests basic hypothesis that the price of medical service and supply of physician by specialties are not pertinent. Being a cross-sectional study, this study can not suggest causal explanations. In the future, further study is needed for causal explanations.
-
Summary
- The Difference in Attitude toward Medical Care between Patients and Physicians.
-
Myung Geun Kang, Jong Ku Park, Han Joong Kim, Myong Sei Sohn, Dal Rae Kim
-
Korean J Prev Med. 1998;31(3):516-539.
-
-
-
Abstract
PDF
- The objective of this study is to identify the difference in attitude toward medical care between patients who visited a university hospital or an oriental medical hospital of oriental medical college, and physicians who engaged in the same hospitals. The subjects of this study were 397 cases who agreed to respond the prepared questionnaire, including 288 patients(146 university hospital utilizers and 142 utilizers for an oriental medical hospital) and 109 physicians(76 physicians and 33 oriental medical doctors). The attitude toward medical care was measured by the structured questionnaire developed for this study, which had high validity and reliability according to factor analysis, item discriminant validity, and Cronbach's alpha coefficients. On the criteria of mean value of care and cure score, the attitude toward medical care was classified into 4 groups encompassing a group with dependent attitude on medical care, a group with skeptical attitude toward it, a group with cure-oriented attitude, and a group with care- preferred attitude. The results of chi-square test, discriminant analysis, and logistic regression analysis were as follows; patients who visited a university hospital, patients who visited an oriental hospital, physicians, and oriental medical doctors included in the group with dependent attitude, the group with cure-oriented attitude, the group with skeptical attitude, and the group with care-preferred attitude, retrospectively. Among the subdomains of care and cure domains, which classified in reference to the result of factor analysis on pilot study, those that patients ranked more importantly than physicians were 'the importance of medical equipment for diagnosis and treatment', 'authority of physician, 'aggressiveness of treatment', 'information giving', 'personal interest' in the case of western medicine. In the case of oriental medicine, those were 'the importance of equipment for diagnosis and treatment', 'aggressiveness of treatment', 'amenities and accessibility', 'coordination of medical staff'. Both physicans and patients put the subdomain, 'physicians' medical knowledge and skillfulness' on the highest rank. The differences in ranking the important attributes of medical care between patients and physicians were apparent in the area of an 'importance of medical equipment for diagnosis and treatment' and so on. It meant that patient had over-expectation on medical care and suggested that the policy on demand side such as the development and dissemination of an evidence-based recommendation protocol for health care consumers might be important in Korea. In addition, regarding the attitude of physicians, during the medical education and training it may be necessary to emphasize the aspect of 'care' of medical care rather than 'cure'. In planning on heath care delivery system, it should be considered that there is a difference in the attitude toward medical care between western medicine and oriental medicine as well as between health care providers and consumers. We expect that more valid measurement tool be developed in this area, which may be major limitation of this study and that this kind of research be expanded into the non-academic settings.
-
Summary
- Comparison of work measures for some physician services in Obstetrics & Gynecology.
-
Yeong Joo Hur, Myong Sei Sohn, Eun Cgeol Park, Hyung Gon Kang, Han Joong Kim
-
Korean J Prev Med. 1995;28(3):623-639.
-
-
-
Abstract
PDF
- We have never seen any method to cope basically with complicated situation and problems around medical reimbursement rates here in Korea since 1977 witnessed by the beginning of medical insurance. By the way researchers concerned are beginning to propose some kinds of innovative and detailed ideas to government these days. They are Diagnosis-related group(DRG)and Resource-based relative value scale(RBRVS). In the light of this situation it is so encouraging that our government can come up with that and move. In case of RBRVS research we have already been reaching even to the level of reviewing and revising methodology for its further development after naive pilot study on internal medicine and general surgery last year. However there might be something different conditions between USA and Korea to apply the same Dr. Hsiao's method and it must be vital to check so called 'total work approach' compared with 'intra-service work approach' before expanding to the whole medical fields. According to the 'Intra-service approach', the physician's work is supposed to be divided into three sub-works by the name of intraservice work, pre, and post service work. These sub-works, again should be merged together to be the pre-postwork subset through some statistical methods of the estimation process applied by Dr. Hsiao's methodology in RBRVS development later on. But in this paper that estimation process was not taken because we could have real values for all of those surveyed items related to just one specialty, OB & GY. Instead, we used some statistical comparison procedures relevant to demographic characteristics, reliability & validity and correlation analysis with American RVU(Relative value unit) between the total work and merged total work from intraservice work approach. The unit of analysis was individual physicians of OB & GY and 300 physicians were selected for each approach through statistical sampling method based on national population of OB & GY physicians in korea. And also with the thankful help of Advisory committee under Korean Association of OB & GY, questionnaires were made and mailed to the subjects, two times. As a result there were not any statistically significant differences in demographic characteristics between the two approaches except for the variable 'Response time for the questionnaire', but in other sections of comparisons, response rate, representative values, reliability & validity test, correlation analysis with American RVU, all showed 'Total approach' was not only more rational and statistically meaningful than ,'Intra-service approach' but also had considerable merits. But we are not absolutely sure about this paper's robustness. Because of some limitations, we'd rather like to suggest further researches should be followed. In that sense the first thing would be a research for the influence of doctor's haracteristics, especially 'frequency' on the rating of work and the way to define total work more clearly.
-
Summary
- A Comparison of Laparoscopic Cholecystectomy with Open Cholecystectomy in a Korean Hospital.
-
Eun Mee Lee, Seung Hum Yu, Myong Sei Sohn, Suk Il Kim
-
Korean J Prev Med. 1995;28(2):325-333.
-
-
-
Abstract
PDF
- Laparoscopic cholecystectomy was introduced into Korea in 1990 and has been rapidly replacing open cholecystectomy when the indications were met. In this study a medical utilization and technology was assessed on the selected hospitalized patients with cholelithiasis who underwent open or laparoscopic cholecystectomy from April 1, 1991 to March 31, 1994. The results are as follows. Despite the low reimbursement rate by the health insurance, the number of laparoscopic cases have been steadily increased. The post-operative days before health insurance coverage were significantly shortened from 8.4 days to 4.6 days. The preoperative days before health insurance coverage were significantly shorted from 8.4 days to 4.0 days. The total length-of-stays in the hospital were also significantly shortened from 15.2 days to 10.7 and 9.8 days in laparoscopic cholecystectomy. The laparoscopic cholecystectomy showed low expenses in all aspects expect the average hospital charges per day. For the hospital to have cost containment, it is more effective if length-of-stay is shorter because of high daily inpatient hospital charge. The laparoscopic cholecystectomy also showed shortened anesthesia time and operation time compared with open cholecystectomy that were statistically significant. The mean anesthesia and operation time for open cholecystectomy were 113.2 and 90.2 minutes but those of laparoscopic cholecystectomy were 105.7 and 68.6 minutes. According to this study the laparoscopic cholecystectomy has reduced the medical expenditure and we recommend this procedure over open cholecystectomy. The further discussion on the different morbidity rate between two types of procedure is essential in providing quality medical care, and to educate specialist.
-
Summary
- Structural Modeling of Health Concern, Health Practice and Health Status of Koreans.
-
Soon Young Lee, Myong Sei Sohn, Chung Mo Nam
-
Korean J Prev Med. 1995;28(1):187-206.
-
-
-
Abstract
PDF
- The purpose of this study was to determine the relationships among the health concern, health practice and health status of Koreans. This study utilized the data from Korean individuals(1,304 male and 1,495 females), whose ages were between 20 and 59. The data were analyzed using SAS version 6.04 and LISREL version 7.13. The analytic methods for the study were chi-square analysis and covariance structural analysis. The results of the study were as follows. (1) There were significant positive relationships between health concern level and health practice index, and between health practice index and self-perceived health status. (2)There were negative relationships between practice index and chronic illness, and between health practice index and acute illness only in female. (3) Based on the findings, the structural model of the health concern, health practice, health status and socioeconomic variables was established and then the covariance structural analysis was used. The higher educational level and economic status were, the higher the health concern was. And urban residents were much more concerned with their health than rural residents. The more persons were concerned with health, the more they did health practices. And the more the health practice was, the higher the health status was. The younger the persons were and the higher the health status of one's family was, the higher the health status was. In female, the higher the economic status was, the higher the health status was.
-
Summary
- An Analysis of Small Area Variations of Hospital Services Utilization in Korea.
-
Woo Hyun Cho, Sun Hee Lee, Eun Cheol Park, Myong Sei Sohn, Se Ra Kim
-
Korean J Prev Med. 1994;27(3):609-626.
-
-
-
Abstract
PDF
- This study was conducted to investigate whether variations in hospital services utilization across small geographic areas in Korea existed, and if so, what factors are responsible for the variation. The claims data of the fiscal year 1992 obtained from the regional health insurance societies were used for the study. Main finding of the research can be summarized as follows: 1. External Quotients (EQ) of hospital expenditure per capita and hospital days per capita were 2.69 and 2.73, and coefficient of variation (CV) were 0.14,both, respectively. The EQ and the CV of admission rate were also 2.71, 0.15. The EQ and the CV of expenditure per admission were 1.73, 0.10 and those of hospital days per admission were 1.29, 0.06. All these statistics were statistically significant and this result provides strong evidence for the existence of small area variations. 2. Comparing patterns of variation among areas, the area which showed higher utilization amounts is cbansungp'o. Koje area, whereas the areas which showed lower utilization amounts are Yongju, Changhung, Miryang, Mokp'o, Koch'ang area. 3. Multivariate analytic methods were used to examine factors related to the variation across areas. In terms of the health resource availability variables, beds per capita or physicians per capita were positively associated with all utilization indices. As for the health service market structure variables, the proportion of health care institutions operating for less than 5 years was positively related to the expenditure per capita, hospital days per capita and expenditure per admission. In addition the proportion of lhe private health care institutions also had a negative relationship with total utilization amount and admission rate and the proportion of physicians under age 40 was negatively associated with expenditure per capita and expenditure per admission. With regard to the socio-demographic characteristics, proportion of medicaid population was positively related to hospital days per capita, and percentage of paved road was positively related to hospital days per admission. As a conclusion, wide variations existed across small areas in Korea and supply factors were found to be important in explaining the variation.
-
Summary
- An Analysis of Determinants of Elderly Medical Costs Inflation Using Deterministic Model.
-
Seung Hum Yu, Myong Sei Sohn, Eun Cheol Park
-
Korean J Prev Med. 1994;27(1):135-144.
-
-
-
Abstract
PDF
- The purpose of this study compares determinants of eldery medical cost inflation with those of other age groups by analysing aggregated data with a deterministic model. The deterministic model of per capita medical cost inflation consists of increases in price, intensity of services, and medical utilization. We used a time series data (1985-1991) from National Medical Insurance and analyzed by age groups. In total population, the average increase rates of inpatient and outpatient medical costs were respectively 9.5% and 8.8% during 6 years and the major cause of inflation was the increase in service intensity in both of inpatient and outpatient cases. But in the population of 65 years old and over, the average increase rates of inpatient and outpatient medical costs were respectively 13.8% and 14.8% and the major cause of inflation was the increase in per-capita medical utilization in both of inpatient and outpatient cases. Also, the increase in service intensity of 65 years old and over was the highest of other age groups. This pattern was similar during study periods. we concluded that the level of medical cost inflation and the determinants in elderly was the highest-especially in per capita medical utilization, therefore, the inflation of medical costs in elderly will be higher than other age groups for the further in Korea.
-
Summary
- Demand Forecasting for Developing Drug Inventory Control Model in a University Hospital.
-
Myong Sei Sohn
-
Korean J Prev Med. 1983;16(1):113-120.
-
-
-
Abstract
PDF
- The main objective of this case study is to develop demand forecasting model for drug inventory control in a university hospital. This study is based on the pertinent records during the period of January 1975 to August 1981 in the pharmacy and stock departments of the hospital. Through the analysis of the above records the author made some major findings as follows: 1. In A.B.C. classification, the biggest demand(A class) consists of 9 items which include 6 items of antibiotics. 2. Demand forecasting level of an index or discrepancy in A class drug compared with real demand for 6 months is average 30.4% by X-11 Arima method and 84.6% by Winter's method respectively. 3. After the correcting by the number of bed, demand forecasting of drug compared with real demand for 6 months is average 23.1% by X-11 Arima method and 46.6% by Winter's method respectively.
-
Summary
|
KSPM
